Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/hahaxiang27/FlowHarnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hahaxiang27/flowharness/speckit-harness-orchestration)<a href="https://agentmods.dev/rules/hahaxiang27/flowharness/speckit-harness-orchestration"><img src="https://agentmods.dev/badge/rules/hahaxiang27/flowharness/speckit-harness-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hahaxiang27/flowharness/speckit-harness-orchestration"><img src="https://agentmods.dev/badge/rules/hahaxiang27/flowharness/speckit-harness-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00495 | $0.00495 |
| Opus 5 | $0.00247 | $0.00247 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
speckit-harness-orchestration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
SpecKit + Harness Orchestration (Step Gate + Dashboard)
This project uses SpecKit + Harness through natural-language requirements. Follow AGENTS.md and these rules in every requirement session.
Step Gate (mandatory)
- One concrete command per user turn unless the user explicitly asks to batch remaining steps.
- After installation or when constitution is missing/incomplete, run
speckit.constitutionfirst, report the result, then stop. - New requirement -> select router mode, publish the concrete
speckit.*/harness.*command flow, initialize dashboard, then stop. - User says
继续/下一步/next/continue-> read the next command fromspecs/{REQUIREMENT_ID}/dashboard-state.json, execute exactly one command, then stop again. - After every concrete command (
speckit.*,harness.*, etc.):- Update
specs/{REQUIREMENT_ID}/dashboard-state.json(.harness/prompts/dashboard-state-updater.md) - Update
specs/{REQUIREMENT_ID}/dashboard.htmlwhen panel content exists (.harness/prompts/dashboard-updater.md) - Hand off with
.harness/prompts/step-gate-handoff.md
- Update
- Low or medium risk never grants auto-continue.
- Router
directmode: implement immediately; skip specs, dashboard, and step gates (.harness/prompts/direct-implement.md).
Dashboard (mandatory for non-direct modes)
After mode selection and before the first concrete command:
- Copy
.harness/templates/dashboard.html->specs/{REQUIREMENT_ID}/dashboard.html - Write
specs/{REQUIREMENT_ID}/dashboard-state.jsonwithworkflow_plan.steps(.harness/prompts/dashboard-plan-init.md) - Tell the user to open the HTML file in a browser; it auto-refreshes from
dashboard-state.json
Runtime Paths
- Harness prompts:
.harness/prompts/ - Harness templates:
.harness/templates/ - Router:
.ai-dev/router/(fallback: toolkitrouter/)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 36 lines · 495 tokens per session scan A f88f35b721c8
speckit-harness-orchestration is a cursor rule published in the GitHub repository hahaxiang27/FlowHarness (4 stars, last pushed 2mo ago), licensed MIT. It adds 495 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.